INDEX

Explanations

numbers and ranges

oai_token-act-pair · gpt-3.5-turbo

numerical values and statistical data points

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sign

-0.63

 minimized

-0.62

 outlawed

-0.62

 erected

-0.60

 testified

-0.58

 signs

-0.58

icable

-0.58

 dismantled

-0.57

 scrut

-0.57

umsy

-0.56

POSITIVE LOGITS

ãĤ´ãĥ³

0.95

cffff

0.82

BIT

0.80

HK

0.78

cffffcc

0.73

soDeliveryDate

0.72

ths

0.71

mph

0.71

oldemort

0.70

tenance

0.70

Activations Density 0.083%

numbers and ranges

numerical values and statistical data points

No Comments

No Known Activations